Source code for

"""Code for querying Latin language dictionaries/lexicons."""

from typing import Optional

import regex
import yaml

from cltk.core.exceptions import CLTKException
from import FetchCorpus
from cltk.utils.file_operations import make_cltk_path
from cltk.utils.utils import query_yes_no

__author__ = ["Clément Besnier <>"]

[docs]class LatinLewisLexicon: """Access a digital form of Charlton T. Lewis's *An Elementary Latin Dictionary* (1890).""" def __init__(self, interactive: bool = True): self.interactive: bool = interactive self.lewis_yaml_fp: str = make_cltk_path( "lat", "lexicon", "cltk_lat_lewis_elementary_lexicon", "lewis.yaml" ) try: self.entries: dict[str, str] = self._load_entries() except FileNotFoundError: do_download: Optional[bool] = None if self.interactive: dl_msg: str = f"This part of the CLTK depends upon Lewis's *An Elementary Latin Dictionary* (1890)." print(dl_msg) dl_question: str = "Do you want to download this?" do_download = query_yes_no(question=dl_question) else: do_download = True if do_download: fetch_corpus: FetchCorpus = FetchCorpus(language="lat") fetch_corpus.import_corpus( corpus_name="cltk_lat_lewis_elementary_lexicon" ) else: raise CLTKException( f"File '{self.lewis_yaml_fp}' is not found. It is required for this class." ) self.entries: dict[str, str] = self._load_entries()
[docs] def lookup(self, lemma: str) -> str: """Perform match of a lemma against headwords. If more than one match, then return the concatenated entries. For example: >>> from import LatinLewisLexicon >>> lll = LatinLewisLexicon(interactive=False) >>> lll.lookup("clemens")[:50] 'clēmēns entis (abl. -tī; rarely -te, L.), adj. wit' >>> all(word in lll.lookup("levis") for word in ["levis","lēvis"]) # Test for concatenated entries True >>> lll.lookup("omnia") '' >>> lll.lookup(".") '' >>> lll.lookup("123") '' >>> lll.lookup("175.") '' >>> lll.lookup("(") # Test for regex special character '' """ if not self.entries: raise CLTKException( "No lexicon entries found in the .yaml file. This should never happen." ) if regex.match(r"^[0-9\.\?,\:;\!\<\>\-]*$", lemma) is not None: return "" lemma = regex.escape(lemma.lower()) keys: list[str] = list(self.entries.keys()) matches: list[str] = [ key for key in keys if regex.match(rf"^{lemma}[0-9]?$", key) ] n_matches: int = len(matches) if n_matches > 1: return "\n".join([self.entries[key] for key in matches]) elif n_matches == 1: return self.entries[matches[0]] else: return ""
[docs] def _load_entries(self) -> dict[str, str]: """Read the yaml file of the lexion.""" with open(self.lewis_yaml_fp) as file_open: entries: dict[str, str] = yaml.load(file_open, Loader=yaml.Loader) return entries